]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cliphunter.py
1 from __future__
import unicode_literals
3 from .common
import InfoExtractor
10 class CliphunterIE(InfoExtractor
):
11 IE_NAME
= 'cliphunter'
13 _VALID_URL
= r
'''(?x)https?://(?:www\.)?cliphunter\.com/w/
15 (?P<seo>.+?)(?:$|[#\?])
18 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
19 'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
23 'title': 'Fun Jynx Maze solo',
24 'thumbnail': r
're:^https?://.*\.jpg$',
29 'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
30 'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
34 'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
35 'thumbnail': r
're:^https?://.*\.jpg$',
40 def _real_extract(self
, url
):
41 video_id
= self
._match
_id
(url
)
42 webpage
= self
._download
_webpage
(url
, video_id
)
44 video_title
= self
._search
_regex
(
45 r
'mediaTitle = "([^"]+)"', webpage
, 'title')
47 gexo_files
= self
._parse
_json
(
49 r
'var\s+gexoFiles\s*=\s*({.+?});', webpage
, 'gexo files'),
53 for format_id
, f
in gexo_files
.items():
54 video_url
= url_or_none(f
.get('url'))
59 format_id
= '%s_%sp' % (fmt
, height
) if fmt
and height
else format_id
62 'format_id': format_id
,
63 'width': int_or_none(f
.get('w')),
64 'height': int_or_none(height
),
65 'tbr': int_or_none(f
.get('br')),
67 self
._sort
_formats
(formats
)
69 thumbnail
= self
._search
_regex
(
70 r
"var\s+mov_thumb\s*=\s*'([^']+)';",
71 webpage
, 'thumbnail', fatal
=False)
77 'age_limit': self
._rta
_search
(webpage
),
78 'thumbnail': thumbnail
,